© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67233
    Prev
    Next
    INDEX
    Explanations

    multinational corporations and spokespersons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {
    -2.83
    -2.83
     the
    -2.73
    9
    -2.72
            
    -2.39
    经常
    -2.38
    2
    -2.33
    </b>
    -2.31
    后
    -2.28
     или
    -2.25
    POSITIVE LOGITS
    艄
    3.19
    縂
    3.13
     公主
    3.03
    '
    2.98
    㩒
    2.44
    彀
    2.38
    曱
    2.38
    畱
    2.38
    …？
    2.30
    좆
    2.30
    Activations Density 0.004%

    No Known Activations